Rendered at 19:55:37 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
Cieric 2 hours ago [-]
I'm still very fascinated by gaussian splatting, but the issue I always run into is the need to use colmap to generate the camera positions and get the initial point cloud. Which colmap effectively still needs Nvidia for dense point clouds last I checked. I'm curious though does anyone have anything else they've tried that worked well? I've tried a few different things (most of the time getting stuck on just compiling the thing) so I'm curious if anyone has any suggestions that I should focus more heavily on getting working. I have some poor quality videos I'd like to try and use and I'm willing to put in some manual work, but it feels like it's all automatic or nothing. Thanks for any suggestions that any of you have.
corysama 36 minutes ago [-]
I know there have been papers and research projects about GS without COLMAP and GS from videos. But, I don't have links handy.
Having this work on Apple metal is huge for the accessibility around training splats. I remember two years ago I needed an RTX Nvidia GPU to run things like splatfacto on nerfstudio. Very neat optimizations as well like the depth map and sky dome, 3dgs has come a long way. Awesome!
mourner 6 hours ago [-]
Oh, a fellow Ukrainian! Was pleasantly surprised to see that fountain on HN — I was just walking around it a few days ago, very nice and peaceful spot this time of year.
fredley 6 hours ago [-]
I thought the picture on your home page was very cool, and then I moused over it. Absolutely incredible.
5 hours ago [-]
miguelraz 3 hours ago [-]
Fantastic demos in Julia, what a treat.
xchip 2 hours ago [-]
Hey Anton, great work as always :)
thimotedupuch 6 hours ago [-]
Great work
chrisjj 5 hours ago [-]
Better? A turn on the spot shows a wreck everywhere but forward.
yorwba 3 hours ago [-]
Those are the areas that are occluded in the input images. If you look at the bushes, you can see that the front is clean while the back is a mess. Probably the starting position could be chosen a bit better.
ghostly_s 25 minutes ago [-]
This raises the question, do any of these projects have workflows for combining images taken from different positions? Or does that just work out of the box? (I have no machines atm with anything better than 10yo eGPUs ;~<)
chrisjj 2 hours ago [-]
The path to left and right is occluded? By what?
ChrisClark 1 hours ago [-]
By not taking photos of it... what else? The data wasn't there, so it couldn't be generated
Actually, this might be a lack of understanding, look up what gaussian splatting is.
Best I can do is link you to https://x.com/RadianceFields and https://radiancefields.com/ They have all the news about GS every day.
AMD GPU (AMDGPU.jl) NVIDIA GPU (CUDA.jl) MacBook GPU(Metal.jl)
Actually, this might be a lack of understanding, look up what gaussian splatting is.
That's not occlusion.